PMID- 37748133
OWN - NLM
STAT- MEDLINE
DCOM- 20240110
LR  - 20240110
IS  - 2473-4209 (Electronic)
IS  - 0094-2405 (Linking)
VI  - 51
IP  - 1
DP  - 2024 Jan
TI  - Automatic dose prediction using deep learning and plan optimization with 
      finite-element control for intensity modulated radiation therapy.
PG  - 545-555
LID - 10.1002/mp.16743 [doi]
AB  - BACKGROUND: Automatic solutions for generating radiotherapy treatment plans using 
      deep learning (DL) have been investigated by mimicking the voxel's dose. However, 
      plan optimization using voxel-dose features has not been extensively studied. 
      PURPOSE: This study aims to investigate the efficiency of a direct optimization 
      strategy with finite elements (FEs) after DL dose prediction for automatic 
      intensity-modulated radiation therapy (IMRT) treatment planning. METHODS: A 
      double-UNet DL model was adapted for 220 cervical cancer patients (200 for 
      training and 20 for testing), who underwent IMRT between 2016 and 2020 at our 
      clinic. The model inputs were computed tomography (CT) slices, organs at risk 
      (OARs), and planning target volumes (PTVs), and the outputs were dose 
      distributions of uniformly generated high-dose region-controlled plans. The FEs 
      were discretized into equal intervals of the dose prediction value within the 
      [OARs avoid PTV(O-P)] and [body avoids OARs & PTV(B-OP)] regions in the test 
      cohort and used to define the objectives for IMRT plan optimization. The plans 
      were optimized using a two-step process. In the beginning, the plans of two extra 
      cases with and without low-dose region control were compared to pursue robust and 
      optimal dose adjustment degree pattern of FEs. In the first step, the mean dose 
      of O-P FEs were constrained to differing degrees according to the pattern. The 
      further the FEs from the PTV, the tighter the constraints. In the second step, 
      the mean dose of O-P FEs from first step were constrained again but weakly and 
      the dose of the B-OP FEs from dose prediction and PTV were tightly regulated. The 
      dosimetric parameters of the OARs and PTV were evaluated and compared using an 
      interstep approach. In another 10 cases, the plans optimized via the 
      aforementioned steps (method 1) were compared with those directly generated by 
      the double-UNet dose prediction model trained by low and high region-controlled 
      plans (method 2). RESULTS: The mean differences in dose metrics between the 
      UNet-predicted dose and the clinical plans were: 0.47 Gy for bladder D(50%) ; 
      0.62 Gy for rectum D(50%) ; 0% for small intestine V(30Gy) ; 1% for small 
      intestine V(40Gy) ; 4% for left femoral head V(30Gy) ; and 6% for right femoral 
      head V(30Gy) . The reductions in mean dose (p < 0.001) after FE-based 
      optimization were: 4.0, 1.9, 2.8, 5.9, and 5.7 Gy for the bladder, rectum, small 
      intestine, left femoral head, and right femoral head, respectively, with flat PTV 
      homogeneity and conformity. Method 1 plans produced lower mean doses than those 
      of method 2 for the bladder (0.7 Gy), rectum (1.0 Gy), and small intestine 
      (0.6 Gy), while maintaining  PTV homogeneity and conformity. CONCLUSION: FE-based 
      direct optimization produced lower OAR doses and adequate PTV doses after DL 
      prediction. This solution offers rapid and automatic plan optimization without 
      manual adjustment, particularly in low-dose regions.
CI  - (c) 2023 American Association of Physicists in Medicine.
FAU - Shen, Yichao
AU  - Shen Y
AD  - Department of Radiation Oncology, Taizhou Hospital, Taizhou, Zhejiang, People's 
      Republic of China.
FAU - Tang, Xingni
AU  - Tang X
AD  - Department of Radiation Oncology, Taizhou Hospital, Taizhou, Zhejiang, People's 
      Republic of China.
FAU - Lin, Sara
AU  - Lin S
AD  - Petrone associates, Staten Island, New York, USA.
FAU - Jin, Xiance
AU  - Jin X
AD  - Radiotherapy Center Department, The First Affiliated Hospital of Wenzhou Medical 
      University, Wenzhou, Zhejiang, People's Republic of China.
FAU - Ding, Jiapei
AU  - Ding J
AD  - Department of Radiation Oncology, Taizhou Hospital, Taizhou, Zhejiang, People's 
      Republic of China.
FAU - Shao, Minghai
AU  - Shao M
AD  - Department of Radiation Oncology, Taizhou Hospital, Taizhou, Zhejiang, People's 
      Republic of China.
LA  - eng
GR  - 21ywb18/Science and Technology Plan Project of Taizhou/
PT  - Journal Article
DEP - 20230925
PL  - United States
TA  - Med Phys
JT  - Medical physics
JID - 0425746
SB  - IM
MH  - Female
MH  - Humans
MH  - *Radiotherapy, Intensity-Modulated/methods
MH  - Radiotherapy Dosage
MH  - Radiotherapy Planning, Computer-Assisted/methods
MH  - *Deep Learning
MH  - *Uterine Cervical Neoplasms/diagnostic imaging/radiotherapy
MH  - Organs at Risk
OTO - NOTNLM
OT  - automatic intensity-modulation radiation therapy planning
OT  - deep-learning dose prediction
OT  - finite element
EDAT- 2023/09/25 18:41
MHDA- 2024/01/10 06:42
CRDT- 2023/09/25 16:33
PHST- 2023/07/21 00:00 [revised]
PHST- 2023/01/03 00:00 [received]
PHST- 2023/08/26 00:00 [accepted]
PHST- 2024/01/10 06:42 [medline]
PHST- 2023/09/25 18:41 [pubmed]
PHST- 2023/09/25 16:33 [entrez]
AID - 10.1002/mp.16743 [doi]
PST - ppublish
SO  - Med Phys. 2024 Jan;51(1):545-555. doi: 10.1002/mp.16743. Epub 2023 Sep 25.